Food internet monitoring system

Abstract

The invention discloses a food internet monitoring system which is composed of a sensing layer, a network layer, a data layer and an application layer. The application layer is composed of a monitoring module, an analysis module, a tracing module and a management module. The problem of data security in the prior art is solved, the purpose of being open to merchants, customers and supervisors at the same time is achieved, all links of a food industry chain are comprehensively covered through a multi-layer architecture, data collection is diversified, conditions of all stages can be mastered in real time, in the aspect of data management, encryption transmission guarantees security, and the data security is improved. Data cleaning ensures purity and effectiveness, data quality is guaranteed through multiple means, visual display of the monitoring module is visual, and it is guaranteed that data is true and reliable due to the fact that a sensor is tampered with and video data integrity verification is achieved.

Description

Technical Field

[0001] The invention relates to the field of food safety monitoring, in particular to a food Internet monitoring system. Background Art

[0002] At present, food safety is particularly important. There are food safety monitoring systems in the prior art, but the food safety monitoring system still has major defects. The first is that the information on the source of food is inaccurate. In order to allow customers to buy problematic products with confidence, there is a problem of tampering with the data of the monitoring system. Second, in the food Internet monitoring system, some data may need to be manually entered, such as food production batch information, initial settings of processing parameters, etc. However, negligence and errors are very likely to occur during the manual entry process. Third, when analyzing multi-dimensional data such as temperature, humidity, and operation time in the food production process, the simple statistical analysis algorithm used may not accurately dig out the potential correlations and trends between the data, resulting in deviations between the analysis results and the actual situation. This deviation may make the decisions made based on the analysis results (such as adjusting food processing technology, optimizing transportation routes, etc.) may not be suitable for the actual situation, and cannot truly reflect the actual status of food production, storage, transportation, etc., affecting the authenticity of the data.

[0003] Moreover, the current food safety monitoring system is more focused on tracing the source of food when customers purchase it, but neglects the manufacturers' warnings on food safety management during production.

[0004] Therefore, there is an urgent need for a food Internet monitoring system that cannot tamper with the data information of both merchants and customers. Summary of the invention

[0005] In order to solve the above-mentioned technical problems, the present invention provides a food Internet monitoring system.

[0006] The technical solution of the present invention is achieved in this way:

[0007] A food Internet monitoring system, consisting of a perception layer, a network layer, a data layer and an application layer;

[0008] The perception layer deploys various sensors and video surveillance cameras at food production sources, processing workshops, storage facilities, logistics and transportation vehicles, and sales terminals. The sensors include but are not limited to temperature sensors, humidity sensors, gas sensors, light sensors, and soil fertility sensors.

[0009] The network layer selects appropriate communication methods to transmit the collected data to the cloud server or local data center according to different application scenarios and sensor types;

[0010] The data layer establishes a large database in a cloud server or a local data center;

[0011] The application layer is composed of a monitoring module, an analysis module, a tracing module and a management module;

[0012] The monitoring module displays the environmental data, temperature, humidity curves and video images of each monitoring point in real time through a visual interface. At the same time, it sets the warning threshold and automatically issues a warning message when the monitoring data exceeds the normal range;

[0013] The analysis module uses big data analysis technology to conduct in-depth analysis of the stored data, build a food traceability system, and realize full traceability from the consumer terminal to the production source based on the collected data; consumers can obtain the detailed history of the food from planting, breeding, processing, transportation to sales, including the time, location, and responsible person of each link by scanning the QR code on the food packaging or entering the food batch information on the relevant APP;

[0014] The management module provides user management, device management, and data management;

[0015] After the perception layer collects data, it transmits the data to the data layer through the network layer for storage, and the data in the data layer is analyzed by the application layer. If the data is abnormal after analysis, an alarm is issued to the user, including the production link, transportation link and sales link, and the user data is continuously monitored.

[0016] Preferably, the monitoring module uses a sensor with an anti-tampering function, which can trigger an alarm and record the status when it is illegally opened or disassembled, and send it to the monitoring platform through the network.

[0017] Preferably, the user management includes user registration, login, and permission setting. Different user roles have different permissions, including customer permissions, production personnel permissions, production management permissions, and supervisor permissions, to ensure the security of system data and the rationality of access.

[0018] Preferably, the data management adopts multiple encryption methods to ensure the security of data transmission, uses the SSL / TLS encryption protocol to encrypt the transmitted data, and uses the encrypted hash algorithm in the blockchain technology to generate a unique and irreversible hash value for each data block, which is transmitted together with the data. After the monitoring platform receives the data, it determines whether the data has been tampered with by comparing the hash value. For video data, streaming media encryption technology is used to divide the video stream into multiple data blocks for encrypted transmission.

[0019] Preferably, the data collection also includes accessing a credible network platform, including a network link to the meteorological department and geographic information system platform of the product production area, to compare the information collected by the sensor.

[0020] Preferably, the analysis module uses big data analysis technology to perform in-depth analysis on the stored data. During the comparative analysis process, if it is found that there are obvious differences between the data of this system and the data of other platforms, abnormal situations are promptly checked, and measures are taken in time to repair or adjust the problems found.

[0021] Preferably, the analysis module analyzes the video data for integrity. If the analysis result is complete, the data is continuously transmitted to the analysis module for in-depth data analysis. If the analysis result is incomplete, a warning is issued and the data is collected again. If the second collection is still incomplete, a detection request is sent to the perception layer to detect the monitoring equipment. If the detection result is that the monitoring is normal, it is determined that the video is missing due to human factors, and a warning is sent to the traceability module.

[0022] Preferably, the analysis module further includes an early warning function unit, which is composed of a data early warning submodule and a video early warning submodule;

[0023] The data warning submodule establishes a dynamic threshold setting mechanism, which dynamically generates more accurate warning thresholds by real-time analysis of the potential impact of food batch characteristics, processing technology changes, and transportation condition fluctuations on food quality, thereby reducing false alarms and missed alarms caused by fixed thresholds;

[0024] Establish a hierarchical early warning system, and classify early warnings into different levels according to the degree to which monitoring data deviate from the normal range and the possible impact on food safety;

[0025] The video warning submodule includes an intelligent video analysis algorithm, which extracts features and recognizes patterns of video images through a deep learning algorithm, and can accurately determine whether there are slight cracks or deformations on the food packaging.

[0026] The analysis module also includes using big data analysis technology to conduct in-depth mining of full-process data to predict possible quality risks that may occur during the production, processing, transportation, and sales of food.

[0027] The present invention solves the data security problems in the prior art and achieves the purpose of being open to merchants, customers and regulators at the same time. The present invention comprehensively covers all links of the food industry chain through a multi-layer architecture, and data collection is diverse, so the situation at each stage can be grasped in real time. In terms of data management, encrypted transmission ensures security, data cleaning ensures purity and effectiveness, and multiple means ensure data quality. The monitoring module has intuitive visualization display, and has anti-tampering sensors and video data integrity verification to ensure that the data is true and reliable. The analysis module deeply mines the data and verifies the authenticity of the data through multi-dimensional correlation analysis. The early warning function unit can dynamically and accurately warn and process in a graded manner, and can also predict quality risks and formulate prevention and control measures to help ensure food safety and optimize operation management. User management reasonably sets permissions and supports multiple users online to meet different needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of a food Internet monitoring system of the present invention. DETAILED DESCRIPTION

[0029] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0030] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0031] The following is a detailed description of the specific implementation methods, features and functions of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0032] Example 1

[0033] like Figure 1 As shown, the food Internet monitoring system of the present invention is composed of a perception layer, a network layer, a data layer and an application layer;

[0034] The perception layer deploys various sensors and video surveillance cameras at food production sources, processing workshops, storage facilities, logistics and transportation vehicles, and sales terminals. The sensors include but are not limited to temperature sensors, humidity sensors, gas sensors, light sensors, and soil fertility sensors. They are used to collect environmental data related to food production, storage, transportation, and sales in real time at the source of agricultural product planting.

[0035] The network layer selects appropriate communication methods to transmit the collected data to the cloud server or local data center according to different application scenarios and sensor types;

[0036] The data layer establishes a large database on a cloud server or a local data center, and uses a combination of relational databases and non-relational databases to store the massive data collected from the perception layer; the collected raw data is pre-processed, including data cleaning, data format unification, data standardization and other operations, so as to improve the accuracy and efficiency of subsequent data analysis;

[0037] The application layer is composed of a monitoring module, an analysis module, a tracing module and a management module;

[0038] The monitoring module displays the environmental data, temperature, humidity curves and video images of each monitoring point in real time through a visual interface, so that regulators, enterprise managers and consumers can intuitively understand the real-time situation of each link in the food industry chain; at the same time, it sets an early warning threshold, and when the monitoring data exceeds the normal range, it automatically sends an early warning message, such as SMS, email, APP push to the relevant responsible person;

[0039] The analysis module uses big data analysis technology to conduct in-depth analysis of the stored data and explore the rules and relationships behind the data. For example, it analyzes the relationship between the growth environment data and the yield and quality of agricultural products in different seasons and regions; optimizes transportation routes, reduces transportation costs and ensures the quality of food during transportation through analysis of logistics and transportation data; and analyzes sales data and consumer feedback data from sales terminals.

[0040] The traceability module builds a food traceability system and realizes full traceability from the consumer terminal to the production source based on the collected data; consumers can obtain the detailed history of the food from planting / breeding, processing, transportation to sales by scanning the QR code on the food packaging or entering the food batch information on the relevant APP, including the time, location, responsible person and other information of each link, thereby enhancing consumers' confidence in food safety;

[0041] The management module provides user management, device management, and data management functions to facilitate daily operation and maintenance of the system.

[0042] After the perception layer collects data, it transmits the data to the data layer through the network layer for storage, and the data in the data layer is analyzed by the application layer. If the data is abnormal after analysis, an alarm is issued to the user, including the production link, transportation link and sales link, and the user data is continuously monitored.

[0043] Preferably, the monitoring module uses a sensor with anti-tampering function, a built-in physical lock or sealing device, and a unique identification code. When it is illegally opened or disassembled, it can trigger an alarm and record the status and send it to the monitoring platform through the network. Regular maintenance and inspection of the sensor is carried out to ensure its normal operation and the accuracy of data collection.

[0044] Preferably, the user management includes user registration, login, and permission setting. Different user roles have different permissions, including customer permissions, production personnel permissions, production management permissions, and supervisor permissions, to ensure the security of system data and the rationality of access. It supports multiple users to access the system online at the same time to meet the needs of different users for food monitoring information; the device management includes the management of user login devices, and setting reminders and verification codes for uncommon login devices.

[0045] Preferably, the data management function adopts multiple encryption methods to ensure the security of data transmission, uses the SSL / TLS encryption protocol to encrypt the transmitted data, and uses the encrypted hash algorithm in the blockchain technology to generate a unique and irreversible hash value for each data block, which is transmitted together with the data. After the monitoring platform receives the data, it determines whether the data has been tampered with by comparing the hash value. For video data, streaming media encryption technology is used to divide the video stream into multiple data blocks for encrypted transmission.

[0046] Preferably, the data collection also includes accessing a credible network platform, including network information of the meteorological department and geographic information system (GIS) platform of the product production area, and comparing the information collected by the sensor. The returned data type may be inconsistent with the data type required by this system. For example, the meteorological data returned by a platform may be a string type, while this system requires a numeric type for subsequent calculation and analysis. At this time, it is necessary to convert the data type, convert the string type data into the corresponding numeric type, and ensure that the data can be used normally in this system.

[0047] Preferably, the data cleaning may introduce some unnecessary interference information or erroneous data in the process of acquiring data from other platforms, such as occasional abnormal weather records on the agricultural meteorological platform (possibly due to equipment failure or temporary interference), mixed advertising information on the agricultural information platform, etc. Data cleaning technology is needed, such as setting a reasonable threshold to filter out these abnormal values ​​or removing irrelevant text content through text processing technology, to ensure that the introduced data is pure and effective.

[0048] Preferably, the analysis module uses big data analysis technology to conduct an in-depth analysis of the stored data. During the comparative analysis, if it is found that the data of this system is significantly different from the data of other platforms, it is necessary to promptly investigate the abnormal situation. First, check whether the sensors of this system are faulty, whether they have been correctly calibrated, and other hardware issues; secondly, check whether there are errors in the data acquisition and processing process, such as whether the data crawling is accurate, whether the data format conversion is correct, and other software issues; finally, consider whether there are special circumstances that cause the difference, such as local sudden natural disasters, human intervention and other factors. Through in-depth investigation of abnormal situations, the authenticity of the data of this system can be accurately judged, and timely measures can be taken to repair or adjust the problems found;

[0049] In addition to comparing single data, multi-dimensional data correlation analysis is also required. For example, different types of data such as meteorological data, geographical data, and growth cycle data are combined to analyze whether the relationship between them conforms to the principles of agricultural science. Taking oat planting as an example, the relationship between these data is analyzed by combining the meteorological data such as temperature, humidity, and light collected by the sensors of this system, as well as the geographical data such as altitude and soil type obtained from the geographic information system platform, and the oat planting growth cycle information obtained from the agricultural information platform. If during the growth of oats, meteorological conditions such as temperature, humidity, and light cooperate with geographical conditions such as altitude and soil type, which can reasonably explain the growth progress and final yield of oats, and are consistent with the growth cycle information provided by the agricultural information platform, then the data collected by this system have a high degree of authenticity, because they can verify each other in multiple dimensions.

[0050] Preferably, the analysis module needs to perform integrity verification on the video data after it is transmitted to the monitoring module, mainly by checking key information such as the video frame rate, resolution, and timestamp to determine whether the video data has been tampered with or partially lost during transmission.

[0051] Preferably, when the analysis module detects abnormalities in key information such as the frame rate, resolution or timestamp of the video, it indicates that the video data may have been tampered with or partially lost during transmission. For example, if it is found that the frame rate of the video suddenly changes from the normal 30 frames / second to 10 frames / second, or the resolution changes from high-definition to blurry, or the timestamp jumps or is missing, it indicates that the video data may have been tampered with during transmission.

[0052] Preferably, the analysis module further includes an early warning function unit, which is composed of a data early warning submodule and a video early warning submodule;

[0053] The data warning submodule establishes a dynamic threshold setting mechanism. Through real-time analysis of the potential impact of food batch characteristics, processing technology changes, and transportation conditions fluctuations on food quality, a more accurate warning threshold is dynamically generated to reduce false alarms and missed reports caused by fixed thresholds; big data analysis technology is used to deeply mine historical data and analyze the characteristics of various monitoring data when food quality problems occur under different combinations of factors. Based on this, a warning threshold model is constructed to automatically adjust the warning threshold according to real-time data and related factors to improve the accuracy and timeliness of warnings; a hierarchical warning system is established to divide warnings into different levels according to the degree to which the monitoring data deviates from the normal range and the degree of possible impact on food safety. For example, a slight deviation from the normal range and a small impact on food quality in the short term is set as a first-level warning, and the relevant responsible person is notified by SMS or APP push to remind attention and continuous monitoring; when the monitoring data has a large deviation, which may cause the risk of food deterioration or quality decline in the short term, it is set as a second-level warning. In addition to push notifications, an email is also required to inform the situation in detail, requiring the responsible person to take immediate measures and feedback the processing results; if the monitoring data seriously exceeds the normal range, it is very likely that serious damage has been caused to food quality;

[0054] The video warning submodule includes an intelligent video analysis algorithm, which can accurately determine whether there are slight cracks or deformations on food packaging by extracting features and recognizing patterns from video images through a deep learning algorithm; it also introduces multimodal video analysis technology to conduct a comprehensive analysis of the visual information and audio information of video images. For example, when the sound of equipment operation is abnormal, even if there is no obvious sign of equipment failure in the video image, audio analysis can be used to determine that there may be equipment hidden dangers, and then issue a warning, thereby improving the comprehensiveness and timeliness of the warning.

[0055] The analysis module also includes using big data analysis technology to conduct in-depth mining of the entire process data to predict the quality risks that may occur in the production, processing, transportation, and sales of food. For example, by analyzing the fluctuations in process parameters in the processing link, changes in environmental conditions in the transportation link, and market feedback in the sales link, a quality risk prediction model is established to predict quality problems such as deterioration, contamination, and poor taste that may occur in food at different stages. Then, according to the prediction results, corresponding prevention and control measures are formulated, such as strengthening quality control of the processing process, optimizing transportation conditions, and improving sales services, so as to reduce food quality risks and ensure food safety.

[0056] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A food Internet monitoring system, characterized in that: It consists of perception layer, network layer, data layer and application layer; The perception layer deploys various sensors and video surveillance cameras at food production sources, processing workshops, storage facilities, logistics and transportation vehicles, and sales terminals. The sensors include but are not limited to temperature sensors, humidity sensors, gas sensors, light sensors, and soil fertility sensors. The network layer selects appropriate communication methods to transmit the collected data to the cloud server or local data center according to different application scenarios and sensor types; The data layer establishes a large database in a cloud server or a local data center; The application layer is composed of a monitoring module, an analysis module, a tracing module and a management module; The monitoring module displays the environmental data, temperature, humidity curves and video images of each monitoring point in real time through a visual interface. At the same time, it sets the warning threshold and automatically issues a warning message when the monitoring data exceeds the normal range; The analysis module uses big data analysis technology to conduct in-depth analysis of the stored data, build a food traceability system, and realize full traceability from the consumer terminal to the production source based on the collected data; consumers can obtain the detailed history of the food from planting, breeding, processing, transportation to sales, including the time, location, and responsible person of each link by scanning the QR code on the food packaging or entering the food batch information on the relevant APP; The management module provides user management, device management, and data management; After the perception layer collects data, it transmits the data to the data layer through the network layer for storage, and the data in the data layer is analyzed by the application layer. If the data is abnormal after analysis, an alarm is issued to the user, including the production link, transportation link and sales link, and the user data is continuously monitored.

2. A food Internet monitoring system according to claim 1, characterized in that: The monitoring module uses a sensor with an anti-tampering function. When it is illegally opened or disassembled, it can trigger an alarm and record the status, which is sent to the monitoring platform through the network.

3. A food Internet monitoring system according to claim 1, characterized in that: The user management includes user registration, login, and permission setting. Different user roles have different permissions, including customer permissions, production personnel permissions, production management permissions, and supervisor permissions, to ensure the security of system data and the rationality of access.

4. A food Internet monitoring system according to claim 1, characterized in that: The data management adopts multiple encryption methods to ensure the security of data transmission, uses the SSL / TLS encryption protocol to encrypt the transmitted data, and uses the encrypted hash algorithm in the blockchain technology to generate a unique and irreversible hash value for each data block, which is transmitted along with the data. After the monitoring platform receives the data, it determines whether the data has been tampered with by comparing the hash value. For video data, streaming media encryption technology is used to divide the video stream into multiple data blocks for encrypted transmission.

5. A food Internet monitoring system according to claim 1, characterized in that: The data collection also includes accessing a credible network platform, including a network link to the meteorological department and geographic information system platform of the product production area, to compare the information collected by the sensors.

6. A food Internet monitoring system according to claim 1, characterized in that: The analysis module uses big data analysis technology to conduct in-depth analysis of the stored data. During the comparative analysis process, if any obvious differences are found between the data of this system and the data of other platforms, abnormal situations will be checked in a timely manner, and measures will be taken in a timely manner to repair or adjust the problems found.

7. A food Internet monitoring system according to claim 1, characterized in that: The analysis module analyzes the video data for integrity. If the analysis result is complete, the data is transmitted to the analysis module for in-depth analysis. If the analysis result is incomplete, a warning is issued and the data is collected again. If the second collection is still incomplete, a detection request is sent to the perception layer to detect the monitoring equipment. If the detection result is that the monitoring is normal, it is determined that the video is missing due to human factors, and a warning is sent to the traceability module.

8. A food Internet monitoring system according to claim 1, characterized in that: The analysis module also includes an early warning function unit, which is composed of a data early warning submodule and a video early warning submodule; The data warning submodule establishes a dynamic threshold setting mechanism, which dynamically generates more accurate warning thresholds by real-time analysis of the potential impact of food batch characteristics, processing technology changes, and transportation condition fluctuations on food quality, thereby reducing false alarms and missed alarms caused by fixed thresholds; Establish a hierarchical early warning system, and classify early warnings into different levels according to the degree to which monitoring data deviate from the normal range and the possible impact on food safety; The video warning submodule includes an intelligent video analysis algorithm, which extracts features and recognizes patterns of video images through a deep learning algorithm, and can accurately determine whether there are slight cracks or deformations on the food packaging.

9. A food Internet monitoring system according to claim 1, characterized in that: The analysis module also includes using big data analysis technology to conduct in-depth mining of full-process data to predict possible quality risks that may occur during the production, processing, transportation, and sales of food.

Images